© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128535
    Prev
    Next
    INDEX
    Explanations

    sentence starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    した後
    -1.55
     sentirse
    -1.52
    ]
    -1.50
     när
    -1.49
    我对
    -1.47
     When
    -1.46
    when
    -1.46
    古风
    -1.45
    5
    -1.44
    韧
    -1.41
    POSITIVE LOGITS
     they
    1.68
     всех
    1.50
    嚷
    1.46
    inée
    1.41
     permite
    1.36
    </strong>
    1.35
    を使った
    1.33
     (‘
    1.31
     plusieurs
    1.29
     alcune
    1.29
    Activations Density 0.000%

    No Known Activations